oh-ci
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes project-defined build and test scripts such as
pnpm typecheck,pnpm test,pnpm lint,cargo check,cargo test, andcargo clippy. - Evidence: Step 6 in
SKILL.mdexplicitly instructs the agent to run these commands and adapt them based on project files likepackage.jsonorMakefile. - Risk: If a Pull Request contains a malicious
package.jsonor test suite, the agent will execute those commands with its current permissions. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external Pull Requests.
- Ingestion points: The skill reads CI logs via
gh api, PR branch code viagit fetch, and project context from.wm/dive_context.md. - Boundary markers: No explicit delimiters or instructions are used to separate untrusted data from the agent's core instructions.
- Capability inventory: The agent has the ability to commit and push code (
git push), create GitHub issues (gh issue create), and execute arbitrary shell commands via the project's build system. - Sanitization: No sanitization or validation of the ingested CI logs or source code is performed before processing.
Audit Metadata